Spaces:
Running
Running
File size: 16,936 Bytes
691dc7c e99df76 691dc7c a9e27c0 691dc7c a9e27c0 691dc7c a9e27c0 691dc7c a9e27c0 691dc7c e99df76 691dc7c a9e27c0 691dc7c a9e27c0 691dc7c a9e27c0 691dc7c a9e27c0 691dc7c a9e27c0 691dc7c a9e27c0 691dc7c a9e27c0 691dc7c a9e27c0 691dc7c a9e27c0 691dc7c a9e27c0 691dc7c | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 | from __future__ import annotations
"""Application workflow for supported local Anthropic web-tool requests."""
import asyncio
import uuid
from collections.abc import AsyncIterator, Mapping
from dataclasses import replace
from datetime import UTC, datetime
from urllib.parse import urlparse, urlsplit
from loguru import logger
from free_claude_code.application.errors import InvalidRequestError
from free_claude_code.application.execution import ProviderExecutor, TokenCounter
from free_claude_code.application.response_collection import collect_response
from free_claude_code.application.routing import RoutedMessagesRequest
from free_claude_code.config.settings import Settings
from free_claude_code.core.anthropic import (
aggregate_anthropic_sse_to_message,
anthropic_status_for_error_type,
)
from free_claude_code.core.anthropic.server_tool_sse import (
ServerToolResponseContext,
server_tool_completion_frames,
server_tool_finish_frames,
server_tool_message_start_frames,
server_tool_result_frames,
server_tool_start_frames,
server_tool_use_frames,
web_fetch_result_block,
web_search_result_block,
web_tool_error_block,
)
from free_claude_code.core.failures import ExecutionFailure, FailureKind
from free_claude_code.core.json_types import JsonObject
from free_claude_code.core.stream_output import StreamOutput
from free_claude_code.core.trace import trace_event
from free_claude_code.core.web_tools import WebSearchResult
from .ports import (
WebFetchEgressPolicy,
WebFetchEgressViolation,
WebToolsPort,
web_fetch_allowed_scheme_set,
)
from .request import (
HIDDEN_WEB_SEARCH_NAME,
AutomaticWebSearchPlan,
WebSearchDomainFilter,
extract_query,
extract_url,
forced_server_tool_name,
forced_tool_turn_text,
plan_automatic_web_search,
unsupported_server_tool_error,
)
class WebToolService:
"""Coordinate one tool request using the originating settings and executor."""
def __init__(
self,
*,
settings: Settings,
client: WebToolsPort,
executor: ProviderExecutor,
token_counter: TokenCounter,
) -> None:
self._client = client
self._executor = executor
self._token_counter = token_counter
self._enabled = settings.enable_web_server_tools
self._verbose_client_errors = settings.log_api_error_tracebacks
self._egress = WebFetchEgressPolicy(
allow_private_network_targets=settings.web_fetch_allow_private_networks,
allowed_schemes=web_fetch_allowed_scheme_set(
settings.web_fetch_allowed_schemes
),
)
def try_stream_messages(
self, routed: RoutedMessagesRequest, *, request_id: str
) -> AsyncIterator[StreamOutput] | None:
"""Validate synchronously; return a lazy body only for handled requests."""
request = routed.request
plan = plan_automatic_web_search(request, web_tools_enabled=self._enabled)
if plan is None:
error = unsupported_server_tool_error(
request, web_tools_enabled=self._enabled
)
if error is not None:
raise InvalidRequestError(error)
tool_name = forced_server_tool_name(request)
if plan is None and tool_name is None:
return None
input_tokens = self._token_counter(
request.messages, request.system, request.tools
)
if plan is not None:
return self._stream_automatic_search(
routed, plan, request_id=request_id, fallback_input_tokens=input_tokens
)
assert tool_name is not None
trace_event(
stage="routing",
event="free_claude_code.api.optimization.web_server_tool",
source="api",
model=routed.resolved.original_model,
)
text = forced_tool_turn_text(request)
tool_input = (
{"query": extract_query(text)}
if tool_name == "web_search"
else {"url": extract_url(text)}
)
return self._stream_local_tool(
tool_name=tool_name,
tool_input=tool_input,
input_tokens=input_tokens,
response_model=routed.resolved.original_model,
)
async def _stream_automatic_search(
self,
routed: RoutedMessagesRequest,
plan: AutomaticWebSearchPlan,
*,
request_id: str,
fallback_input_tokens: int,
) -> AsyncIterator[StreamOutput]:
"""Keep one provider decision private, then replay it or execute search."""
translated = replace(routed, request=plan.request)
trace_event(
stage="routing",
event="free_claude_code.api.web_search.automatic_recognized",
source="api",
request_id=request_id,
model=routed.resolved.original_model,
)
provider_stream = self._executor.stream_messages(
translated,
raw_log_payload=plan.request.model_dump,
request_id=request_id,
)
chunks = await collect_response(provider_stream, protocol="messages")
message, stream_error, _complete = await aggregate_anthropic_sse_to_message(
_iterate_chunks(chunks)
)
if stream_error is not None:
raise _execution_failure_from_stream_error(stream_error)
tool_calls = _tool_calls(message)
if not tool_calls:
trace_event(
stage="execution",
event="free_claude_code.api.web_search.automatic_declined",
source="api",
request_id=request_id,
model=routed.resolved.original_model,
)
for chunk in chunks:
yield StreamOutput((chunk,))
return
queries: list[str] = []
for call in tool_calls:
if call.get("name") != HIDDEN_WEB_SEARCH_NAME:
raise _protocol_failure(
"Upstream model returned an unexpected tool for automatic WebSearch.",
request_id=request_id,
)
arguments = call.get("input")
if not isinstance(arguments, dict) or set(arguments) != {"query"}:
raise _protocol_failure(
"Upstream model returned malformed arguments for automatic WebSearch.",
request_id=request_id,
)
raw_query = arguments.get("query")
if not isinstance(raw_query, str) or not raw_query.strip():
raise _protocol_failure(
"Upstream model returned an empty query for automatic WebSearch.",
request_id=request_id,
)
queries.append(raw_query.strip())
provider_usage = _provider_usage(message)
input_tokens = _integer_field(provider_usage, "input_tokens")
if input_tokens is None:
input_tokens = fallback_input_tokens
trace_event(
stage="execution",
event="free_claude_code.api.web_search.automatic_selected",
source="api",
request_id=request_id,
model=routed.resolved.original_model,
)
message_id = f"msg_{uuid.uuid4()}"
contexts = [
ServerToolResponseContext(
message_id=message_id,
tool_id=f"srvtoolu_{uuid.uuid4().hex}",
model=routed.resolved.original_model,
tool_name="web_search",
tool_input={"query": query},
input_tokens=input_tokens,
provider_usage=provider_usage,
)
for query in queries
]
executed = min(len(contexts), plan.max_uses or len(contexts))
for frame in server_tool_message_start_frames(contexts[0]):
yield StreamOutput((frame,))
limit = asyncio.Semaphore(4)
async def search_one(
context: ServerToolResponseContext,
) -> tuple[JsonObject, str]:
async with limit:
return await self._search_result(context, plan.domains)
summaries: list[str] = []
async with asyncio.TaskGroup() as group:
tasks = [
group.create_task(search_one(context))
for context in contexts[:executed]
]
for index, context in enumerate(contexts):
for frame in server_tool_use_frames(context, index=index * 2):
yield StreamOutput((frame,))
if index < executed:
result_block, summary = await tasks[index]
else:
result_block = web_tool_error_block(
context, error_code="max_uses_exceeded"
)
summary = (
f"Web search limit reached for: {context.tool_input['query']}"
)
for frame in server_tool_result_frames(
result_block, index=index * 2 + 1
):
yield StreamOutput((frame,))
summaries.append(summary)
for frame in server_tool_finish_frames(
contexts[0],
summary="\n\n".join(summaries),
index=len(contexts) * 2,
request_count=executed,
):
yield StreamOutput((frame,))
trace_event(
stage="execution",
event="free_claude_code.api.web_search.automatic_completed",
source="api",
request_id=request_id,
model=routed.resolved.original_model,
)
async def _stream_local_tool(
self,
*,
tool_name: str,
tool_input: dict[str, str],
input_tokens: int,
response_model: str,
provider_usage: Mapping[str, object] | None = None,
domains: WebSearchDomainFilter | None = None,
) -> AsyncIterator[StreamOutput]:
context = ServerToolResponseContext(
message_id=f"msg_{uuid.uuid4()}",
tool_id=f"srvtoolu_{uuid.uuid4().hex}",
model=response_model,
tool_name=tool_name,
tool_input=tool_input,
input_tokens=input_tokens,
provider_usage=provider_usage,
)
for frame in server_tool_start_frames(context):
yield StreamOutput((frame,))
if tool_name == "web_search":
result_block, summary = await self._search_result(context, domains)
else:
try:
fetched = await self._client.fetch(
tool_input["url"], egress=self._egress
)
result_block = web_fetch_result_block(
context, fetched, retrieved_at=datetime.now(UTC).isoformat()
)
summary = fetched.data
except Exception as error:
_log_web_tool_failure(tool_name, error, fetch_url=tool_input["url"])
result_block = web_tool_error_block(context)
summary = _web_tool_client_error_summary(
tool_name, error, verbose=self._verbose_client_errors
)
for frame in server_tool_completion_frames(
context, result_block, summary=summary
):
yield StreamOutput((frame,))
async def _search_result(
self,
context: ServerToolResponseContext,
domains: WebSearchDomainFilter | None,
) -> tuple[JsonObject, str]:
query = context.tool_input["query"]
try:
results = await self._client.search(query)
if domains is not None:
results = _filter_results(results, domains)
return web_search_result_block(context, results), _search_summary(
query, results
)
except Exception as error:
_log_web_tool_failure("web_search", error, fetch_url=None)
return web_tool_error_block(context), _web_tool_client_error_summary(
"web_search", error, verbose=self._verbose_client_errors
)
def _search_summary(query: str, results: list[WebSearchResult]) -> str:
if not results:
return f"No web search results found for: {query}"
lines = [f"Search results for: {query}"]
for index, result in enumerate(results, start=1):
lines.append(f"{index}. {result.title}\n{result.url}")
return "\n\n".join(lines)
async def _iterate_chunks(chunks: tuple[str, ...]) -> AsyncIterator[str]:
for chunk in chunks:
yield chunk
def _tool_calls(message: Mapping[str, object]) -> list[dict[str, object]]:
content = message.get("content")
if not isinstance(content, list):
return []
calls: list[dict[str, object]] = []
for block in content:
if not isinstance(block, dict) or block.get("type") != "tool_use":
continue
calls.append({str(key): value for key, value in block.items()})
return calls
def _provider_usage(message: Mapping[str, object]) -> dict[str, object]:
usage = message.get("usage")
if not isinstance(usage, dict):
return {}
return {str(key): value for key, value in usage.items()}
def _integer_field(values: Mapping[str, object], key: str) -> int | None:
value = values.get(key)
return value if isinstance(value, int) and not isinstance(value, bool) else None
def _filter_results(
results: list[WebSearchResult],
domains: WebSearchDomainFilter,
) -> list[WebSearchResult]:
if not domains.allowed and not domains.blocked:
return results
return [result for result in results if _hostname_is_allowed(result.url, domains)]
def _hostname_is_allowed(url: str, domains: WebSearchDomainFilter) -> bool:
hostname = urlsplit(url).hostname
if hostname is None:
return False
try:
normalized = hostname.encode("idna").decode("ascii").lower()
except UnicodeError:
return False
if domains.allowed and not any(
_is_hostname_or_subdomain(normalized, domain) for domain in domains.allowed
):
return False
return not any(
_is_hostname_or_subdomain(normalized, domain) for domain in domains.blocked
)
def _is_hostname_or_subdomain(hostname: str, domain: str) -> bool:
return hostname == domain or hostname.endswith(f".{domain}")
def _execution_failure_from_stream_error(
error: Mapping[str, object],
) -> ExecutionFailure:
raw_type = error.get("type")
error_type = raw_type if isinstance(raw_type, str) else "api_error"
raw_message = error.get("message")
message = (
raw_message
if isinstance(raw_message, str) and raw_message.strip()
else "Provider request failed unexpectedly."
)
status = anthropic_status_for_error_type(error_type)
kind = {
400: FailureKind.INVALID_REQUEST,
401: FailureKind.AUTHENTICATION,
402: FailureKind.PERMISSION,
403: FailureKind.PERMISSION,
404: FailureKind.INVALID_REQUEST,
413: FailureKind.INVALID_REQUEST,
429: FailureKind.RATE_LIMIT,
504: FailureKind.TIMEOUT,
529: FailureKind.OVERLOADED,
}.get(status, FailureKind.UPSTREAM)
return ExecutionFailure(
kind=kind,
status_code=status,
message=message,
retryable=False,
)
def _protocol_failure(message: str, *, request_id: str) -> ExecutionFailure:
return ExecutionFailure(
kind=FailureKind.UPSTREAM,
status_code=500,
message=f"{message}\n\nRequest ID: {request_id}",
retryable=False,
)
def _safe_public_host_for_logs(url: str) -> str:
host = urlparse(url).hostname or ""
return host[:253]
def _log_web_tool_failure(
tool_name: str,
error: BaseException,
*,
fetch_url: str | None = None,
) -> None:
exc_type = type(error).__name__
if isinstance(error, WebFetchEgressViolation):
host = _safe_public_host_for_logs(fetch_url) if fetch_url else ""
logger.warning(
"web_tool_egress_rejected tool={} exc_type={} host={!r}",
tool_name,
exc_type,
host,
)
return
if tool_name == "web_fetch" and fetch_url:
logger.warning(
"web_tool_failure tool={} exc_type={} host={!r}",
tool_name,
exc_type,
_safe_public_host_for_logs(fetch_url),
)
else:
logger.warning("web_tool_failure tool={} exc_type={}", tool_name, exc_type)
def _web_tool_client_error_summary(
tool_name: str,
error: BaseException,
*,
verbose: bool,
) -> str:
if verbose:
return f"{tool_name} failed: {type(error).__name__}"
return "Web tool request failed."
|